Experiment Complete Published
Ollama 0.40.13 on M5 Max · 64 GiB, Metal
LFM2.5 2.6B as Q4_K_M (4-bit), archive 2048 input / 128 output: a 2048-token prompt and 128 tokens out. Measured 12 Nov 2026, 23:15 UTC by Glenn Sonna, Xybrid.
Doesn’t count in rankings: Its output check failed: 8/9 of the checks the model passes at BF16; needs 8 and the mandatory ones (needle-start, continuation-128). Left out, failed by every BF16 configuration: color, sort, needle-end.
Experiment id s3-lfm2.5-2.6b-4-bit-ollama-2048
Summary
Over 6 valid trials of 6 attempted (6 planned), computed from the raw trials below.
| Metric | Median | Range | Mean ± SD | Quartiles |
|---|---|---|---|---|
| Decode speed tok/s, higher is better | 224.1 | 223.7–225.4 | 224.4 ± 0.7 | 224.0–224.8 |
| Time to first token ms, lower is better | 297 | 296–298 | 297 ± 0.5 | 296–297 |
| Peak memory GiB, lower is better | 1.86 | 1.86–1.86 | 1.86 ± 0.00 | 1.86–1.86 |
| Prefill speed tok/s, higher is better | 6,966 | 6,939–6,972 | 6,962 ± 12.7 | 6,958–6,971 |
Trials, metric by metric
The line runs from the lowest to the highest valid trial, the dot is the median and each tick is one trial.
Every trial
Raw token counts and durations, with the speeds computed from them. Invalid trials stay in the record with their reason; they are left out of the summary, never silently dropped.
| Trial | Time to first token ms | Prefill tok/s | Decode tok/s | Peak memory GiB | Thermal | Note |
|---|---|---|---|---|---|---|
| 1 | 297 | 6,9572,048 tok in 294 ms, engine | 224.0127 tok in 567 ms, engine | 1.86 | nominal → nominal | |
| 2 | 297 | 6,9612,048 tok in 294 ms, engine | 224.1127 tok in 567 ms, engine | 1.86 | nominal → nominal | |
| 3 | 296 | 6,9712,048 tok in 294 ms, engine | 224.2127 tok in 566 ms, engine | 1.86 | nominal → nominal | |
| 4 | 296 | 6,9722,048 tok in 294 ms, engine | 225.4127 tok in 563 ms, engine | 1.86 | nominal → nominal | |
| 5 | 298 | 6,9392,048 tok in 295 ms, engine | 223.7127 tok in 568 ms, engine | 1.86 | nominal → nominal | |
| 6 | 296 | 6,9702,048 tok in 294 ms, engine | 225.0127 tok in 565 ms, engine | 1.86 | nominal → nominal |
Caveats
- Publisher cards identify the base model but do not always pin the exact export source checkpoint revision.
- Engines may differ in quantization scheme, effective KV cache precision, kernels, and activations.
Configuration
Device
- Device
- Apple Mac17,6
- Cohort
- Apple silicon Macs (desktop)
- SoC
- Apple M5 Max
- CPU
- 18-core Apple CPU
- GPU
- Not recorded
- NPU
- Not recorded
- RAM
- 64.00 GiB
- OS
- macOS 27.2.0 (26B123)
- Kernel
- 27.2.0
- Power
- mains
- Low power mode
- No
- Performance mode
- Not recorded
Engine
- Engine
- Ollama
- Maintainer
- Ollama
- License
- MIT, open source
- Version
- 0.40.13
- Commit
- Not recorded
- Binary SHA-256
- 270089e59e1d411ac4d0987154b4e95f48b29a81c9d274833c6b766d6df88300
- Built from
- release
- Build flags
- None
- Backend
- Metal
- Threads
- Not recorded
- Interface
- http-server
- Settings in effect
- backend=metal model=xybrid-02a8b7e17487d326 blob=sha256-02a8b7e17487d326e46d68ce0ba24211e1b80a14c4cd0597fa73c1cd697f52ed offloaded_layers=31 bos_stripped=true llama_server.host=127.0.0.1 llama_server.no-webui=true llama_server.offline=true llama_server.c=4096 llama_server.np=1 llama_server.log-verbosity=4 llama_server.no-log-prefix=true llama_server.no-log-timestamps=true llama_server.cache-type-k=f16 llama_server.cache-type-v=f16 llama_server.flash-attn=on llama_server.b=512 llama_server.ub=512 llama_server.context-shift=true llama_server.keep=4 env.OLLAMA_KEEP_ALIVE=-1 env.OLLAMA_FLASH_ATTENTION=1 env.OLLAMA_KV_CACHE_TYPE=f16 env.OLLAMA_NOHISTORY=1 env.OLLAMA_NUM_PARALLEL=1 env.OLLAMA_MAX_LOADED_MODELS=1 env.LLAMA_ARG_CACHE_RAM=0
Model and weights
- Base model
- LFM2.5 2.6B (LFM2.5, 2.6B)
- Upstream
- LiquidAI/LFM2.5-2.6B@7141b56cd4650af95c7c7b86983443aed050c96a
- Weights
- LiquidAI/LFM2.5-2.6B-GGUF@e7caca5d835a3901a8e0d63e94009429bafafdfc
- Format
- gguf
- File 1
- LFM2.5-2.6B-Q4_K_M.gguf · 1.56 GiB · sha256 02a8b7e17487d326e46d68ce0ba24211e1b80a14c4cd0597fa73c1cd697f52ed
- File 2
- README.md · 3,068 bytes · sha256 d08b79260b3998e96792777085e4175b730667568f3a953ad4ac9099cfa27056
- Quantization
- Q4_K_M (4-bit)
- Weight bits
- 4
- Group size
- Not recorded
- KV cache
- f16
- Conversion
- Published upstream by LiquidAI
- Conversion command
- Not recorded
Workload
- Workload
- Archive 2048 input / 128 output
- Prompt
- 2,048 tokens, from prompts/source.txt
- Prompt SHA-256
- c10d1b7bef62d95322f8f8d229dc66118d9375107bdc49b06f76287d058b2f6c
- Chat template
- ea663864491de7ade391839479860ca95541f892f72665c73251fbd4643b1bef
- Output
- 128 tokens, ignoring end of sequence
- Context length
- 4,096
- Batch size
- 1
- Sampling
- Greedy
- Timing
- One streamed request per trial
- Warmup
- 2 runs, not counted
- Trials planned
- 6
- Cooldown
- 15 s between trials
Conditions
- Ambient
- Not recorded
- Thermal at start
- nominal
- Thermal at end
- nominal
- Thermal gate
- macOS thermal state nominal
- Throttling detected
- No
Provenance
- Measured by
- Glenn Sonna, Xybrid
- Operator affiliation
- Xybrid
- Run at
- 12 Nov 2026, 23:15 UTC
- Harness
- xybrid-bench 0.4.0 (bde6325f3e1d617ca13cbb1d008164ccc9b7b7c3)
- Methodology
- v0.6
- Publication
- published
- Published
- 16 Nov 2026, 10:23 UTC
- Reviewed by
- Glenn Sonna
Output check
- Result
- Failed
- Method
- sanity-v1-bf16-reference
- Reference
- checks/sanity-v1.json
- Reference SHA-256
- a702dee079525ae0ec90465b1c9e26052c99cb3e1c53e83dea05be4c194fc7ca
- Required passing checks
- 8
- Check arithmetic
- Passed · sha256 68ce25cb2c4b530f85434cd352428b022149c641163300e566f4f9ee9d789bcf
- Check capital
- Passed · sha256 7a3bb1905f2039638dff3f8a3da57abf7b1da32596b04c5ed04c5296f155196a
- Check opposite
- Passed · sha256 69a13e1ba8e284fcc26068ec8aa80e8a7e7f8bbebe86dc7a45424411198a6859
- Check weekday
- Passed · sha256 b8c6a621f6e216db1d214b8d906c759be744ff3abc6e41f979ff0d24575cbbcd
- Check color
- Failed · sha256 fe08d89d0b006dfadf3ef0dfdad25eded8e6238dcd5af7ea93748aaec2d565fd
- Check sort
- Failed · sha256 f3e9a127eb72ee656a49ae07958aff2ae3343aa843f5b3abc9ae9de9f560a4f8
- Check animal
- Passed · sha256 3e9114b6df29561433c18b3a6abce2c635fbd8e9ff25b5fcee93149bfea52859
- Check word
- Passed · sha256 d1bf31457072aaa4c116ea5819a644456232fdd87b15203d3eafdd5e541f4e61
- Check copy
- Passed · sha256 d8c711dfa5fef68d1d0f86320daeca065b91bc8d0dbcea210f8b9ef80eefc6c2
- Check needle-start
- Passed · sha256 e4b695d890438ad108a6fd9cb2e39bf857a00a883f231741c1f92416c1b218c4
- Check needle-end
- Passed · sha256 34b7b9e17d75628c346994d8be48566a2dd011ba8533dc75fc33a579ee705365
- Check continuation-128
- Failed · sha256 da3683ef8034e95c52683294949e3e9c606f4429c3d6e782c3fcadaa386ce12a
- Detail
- 8/9 of the checks the model passes at BF16; needs 8 and the mandatory ones (needle-start, continuation-128). Left out, failed by every BF16 configuration: color, sort, needle-end.
Reproduce it
pnpm bench run --plan plans/s3-lfm2.5-2.6b-4-bit.json
Three palindromic blocks per quantization class and workload; load, two warmups, one trial, unload per turn.
Raw data
- This record, as committed JSON, schema v0.3.0
- Complete finalized session evidence raw ·
sha256 d84c658e7b83…